Training in progress, step 11500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:932444defba9a5b8dd44f88b8bcb52ab659664a28676382e15a373cf36bf6034
+oid sha256:951de22caec4595c4ffeef6e17bf618ff4c5009026d3bf61fbbf6c21e394a753
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80012b6836a364fdec2135af886ce664e83e4046832b07a32b6501d8f4ef656
+oid sha256:94352e8877cdd376b4e0992fbcd1a31c79a5cbb8edc941287bffbb6813ad2fd9
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d7167878bddb7c0a88c66ad0b0be73885dac80e1980348d5e68d660c4a16ce9
+oid sha256:7ce35713c6cfde8b254092a62a162b21058e7d89b73dff276ea2ee9e65249418
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42adf2998e15e06307e725ba7dcb6c52fc0a94a297e1345e89da412c057a53a6
+oid sha256:7733da2de8ba0d811f711ea7fdb6cdb69bbfeb6cd9a30bcfdad50f83ead3040c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f034f97f7b7aead49a2646d657b2abae10ec15daef82d04e9386fb7172dbeddc
+oid sha256:d47850787d7113906407c13287aaa8fd754cf26d87c84c8d6940554fabd6e6fa
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 11000,
   "best_metric": 4.307990074157715,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-11000",
-  "epoch": 0.8460887624028921,
+  "epoch": 0.8845473425121144,
   "eval_steps": 250,
-  "global_step": 11000,
+  "global_step": 11500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1900,6 +1900,92 @@
       "eval_samples_per_second": 53.273,
       "eval_steps_per_second": 13.318,
       "step": 11000
+    },
+    {
+      "epoch": 0.8499346204138143,
+      "grad_norm": 5.336431503295898,
+      "learning_rate": 8.36983934414176e-05,
+      "loss": 4.3977,
+      "step": 11050
+    },
+    {
+      "epoch": 0.8537804784247366,
+      "grad_norm": 4.175157070159912,
+      "learning_rate": 8.344104996139847e-05,
+      "loss": 4.4053,
+      "step": 11100
+    },
+    {
+      "epoch": 0.8576263364356588,
+      "grad_norm": 4.384688377380371,
+      "learning_rate": 8.318370648137934e-05,
+      "loss": 4.26,
+      "step": 11150
+    },
+    {
+      "epoch": 0.8614721944465811,
+      "grad_norm": 3.6022467613220215,
+      "learning_rate": 8.292636300136024e-05,
+      "loss": 4.2993,
+      "step": 11200
+    },
+    {
+      "epoch": 0.8653180524575033,
+      "grad_norm": 4.252429485321045,
+      "learning_rate": 8.266901952134112e-05,
+      "loss": 4.299,
+      "step": 11250
+    },
+    {
+      "epoch": 0.8653180524575033,
+      "eval_loss": 4.334308624267578,
+      "eval_runtime": 18.9071,
+      "eval_samples_per_second": 52.89,
+      "eval_steps_per_second": 13.223,
+      "step": 11250
+    },
+    {
+      "epoch": 0.8691639104684256,
+      "grad_norm": 3.4003775119781494,
+      "learning_rate": 8.241167604132201e-05,
+      "loss": 4.2806,
+      "step": 11300
+    },
+    {
+      "epoch": 0.8730097684793477,
+      "grad_norm": 3.7436835765838623,
+      "learning_rate": 8.215433256130289e-05,
+      "loss": 4.2694,
+      "step": 11350
+    },
+    {
+      "epoch": 0.8768556264902699,
+      "grad_norm": 2.8963701725006104,
+      "learning_rate": 8.189698908128376e-05,
+      "loss": 4.362,
+      "step": 11400
+    },
+    {
+      "epoch": 0.8807014845011922,
+      "grad_norm": 3.3496339321136475,
+      "learning_rate": 8.163964560126465e-05,
+      "loss": 4.3698,
+      "step": 11450
+    },
+    {
+      "epoch": 0.8845473425121144,
+      "grad_norm": 4.4007487297058105,
+      "learning_rate": 8.138230212124553e-05,
+      "loss": 4.2994,
+      "step": 11500
+    },
+    {
+      "epoch": 0.8845473425121144,
+      "eval_loss": 4.315768241882324,
+      "eval_runtime": 18.8056,
+      "eval_samples_per_second": 53.176,
+      "eval_steps_per_second": 13.294,
+      "step": 11500
     }
   ],
   "logging_steps": 50,